CT衍生影像组学特征对提取库与灰度离散化的敏感性:免疫生物标志物发现背景下的研究
本研究基于164例接受免疫检查点抑制剂治疗的非小细胞肺癌患者治疗前CT,比较Pyradiomics与RaCat两个库提取的影像组学特征与无进展生存期、PD-L1表达及CD8计数关联的方向性差异,并分析灰度离散化参数的影响,强调标准化影像组学特征对生物标志物研究的重要性。
要点
- Pyradiomics与RaCat两库共提取1224与441个特征,仅75个为共同特征。
- 特征与临床终点的关联方向高度依赖提取库,Pyradiomics更多特征与PFS相关,RaCat与PD-L1关联更强。
- 基于强度的特征在Pyradiomics不同灰度离散化参数下与临床终点关联一致。
核心结论
- 影像组学库的异质性和灰度离散化参数会影响特征选择与生物标志物预测模型开发,标准化影像组学特征对以影像为终点的转化研究至关重要。
研究设计与样本
- 回顾性队列研究,纳入164例接受免疫检查点抑制剂治疗的非小细胞肺癌患者,从治疗前CT提取影像组学特征,比较Pyradiomics与RaCat两个库,采用单变量模型评估特征与无进展生存期、PD-L1表达及CD8计数的关联。
诊断标准与关键数值
- Pyradiomics提取1224个影像组学特征,RaCat提取441个,两库共有特征75个。
- Pyradiomics特征中与PFS有统计学关联的特征数量更多,RaCat特征与PD-L1表达的关联更强。
- 基于强度的特征在Pyradiomics不同灰度离散化参数下与临床终点的关联保持一致。
临床应用与阅片要点
- 作者强调需选择稳定的CT手工特征来构建免疫治疗生物标志物,这是多机构验证影像生物标志物的必要前提。
- 作者指出影像组学库和灰度离散化参数的异质性会影响特征选择与预测模型开发,标准化影像组学特征有助于以影像为终点的转化研究。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: Radiomics can predict patient outcomes by automatically extracting a large number of features from medical images. This study is aimed to investigate the sensitivity of radiomics features extracted from 2 different pipelines, namely, Pyradiomics and RaCat, as well as the impact of gray-level discretization on the discovery of immune checkpoint inhibitors (ICIs) biomarkers.
METHODS: A retrospective cohort of 164 non-small cell lung cancer patients administered with ICIs was used in this study. Radiomic features were extracted from the pre-treatment CT scans. Univariate models were used to assess the association of common radiomics features between 2 libraries with progression-free survival (PFS), programmed death ligand 1 (PD-L1), and tumour infiltrating lymphocytes (CD8 counts). In addition, we also examined the impact of gray-level discretization incorporated in Pyradiomics on the robustness of features across various clinical endpoints.
RESULTS: We extracted 1224, 441 radiomic features using Pyradiomics and RaCat, respectively. Among these, 75 features were found to be common between the 2 libraries. Our analysis revealed that the directionality of association between radiomic features and clinical endpoints is highly dependent on the library. Notably, a larger number of Pyradiomics features were statistically associated with PFS, whereas RaCat features showed a stronger association with PD-L1 expression. Furthermore, intensity-based features were found to have a consistent association with clinical endpoints regardless of the gray-level discretization parameters in Pyradiomics-extracted features.
CONCLUSIONS: This study highlights the heterogeneity of radiomics libraries and the gray-level discretization parameters that will impact the feature selection and predictive model development for biomarkers. Importantly, our work highlights the significance of standardizing radiomic features to facilitate translational studies that use imaging as an endpoint.
ADVANCES IN KNOWLEDGE: Our study emphasizes the need to select stable CT-derived handcrafted features to build immunotherapy biomarkers, which is a necessary precursor for multi-institutional validation of imaging biomarkers.
引用
- Ebrahimpour L, Lemaréchal Y, Yolchuyeva S, et al. Sensitivity of CT-derived radiomic features to extraction libraries and gray-level discretization in the context of immune biomarker discovery. Br J Radiol. 2024. PMID: 39287013. doi:10.1093/bjr/tqae187
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。